Sign in

Private Post-GAN Boosting

By Marcel Neunhoeffer and others
Differentially private GANs have proven to be a promising approach for generating realistic synthetic data without compromising the privacy of individuals. Due to the privacy-protective noise introduced in the training, the convergence of GANs becomes even more elusive, which often leads to poor utility in the output generator at the... Show more
March 25, 2021
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Private Post-GAN Boosting
Click on play to start listening